FastVLM 7B — Hardware Requirements & GPU Compatibility
Chat
FastVLM 7B is a 7.8B-parameter open language model from Apple. It supports a context window of up to 32,768 tokens. At BF16 it needs about 15.95 GB of VRAM — see which GPUs and Macs can run it below.
Runs well on a 24 GB GPU
Runs from 16 GB (BF16 · 2K)Best on 24 GB (BF16 · ~41 tok/s · 32K)Macs from 24 GB (BF16 · ~14 tok/s)
apple-amlr
Reference GPU · RTX 4090 24 GB
Estimates, ±20% · how we estimate
Run FastVLM 7B
One recommended way. Every other method, OS and quant is in the step-by-step guide.Each way opens a step-by-step guide for your OS and quant.
Recommended
vllm serve apple/FastVLM-7B --max-model-len 16384vLLM repo with its own quantisation
Download: Weights on Hugging Face
Ways to runOther ways
each opens step-by-stepRun in cloud
Runs on RTX 3090 (24 GB) (7 GB headroom) · BF16
- Generation speed
- ~38 tok/s
- generation speed
- Cost per 1M output tokens
- $1.44
- per 1M output tokens
How Much VRAM Does FastVLM 7B Need?
Select a quantization level; the listed hardware adheres to it.
| Quantization | VRAM | +32K | On RTX 4090 (reference) | |
|---|---|---|---|---|
| 15.9 GB | 17.7 GB | 16-bit · bfloat — Brain floating point 16 — preferred for training | Fits: 32K context · ~41 tok/s |
Selected BF16
Brain floating point 1616.8GBat 16K context
- Weights
- 15.5 GB
- KV cache
- 0.9 GB
- Overhead
- 0.3 GB
Fits RTX 4090 (reference) · 7.2 GB free · ~41 tok/s
≥50 tok/s needs ≥1.23 TB/s · RTX 5090 ~73
Which Hardware Can Run FastVLM 7B?
BF16 · 15.9 GBFastVLM 7B (BF16) requires 15.9 GB of VRAM to load the model weights. For comfortable inference with headroom for KV cache and system overhead, 21+ GB is recommended. Using the full 33K context window can add up to 1.8 GB, bringing total usage to 17.7 GB. 26 GPUs can run it, including NVIDIA GeForce RTX 5090, NVIDIA GeForce RTX 3090 Ti, NVIDIA GeForce RTX 5080. 122 devices with unified memory can run FastVLM 7B, including Mac Studio (M3 Ultra, 256GB), Mac Studio (M3 Ultra, 512GB), Mac Mini M5 Pro (24 GB).
20 GB
fits · 3.2 GB free · up to 32K ctx
1 GPU
RX 7900 XT~30Simulate output on RX 7900 XT32–40 GB
fits · 15.2 GB free · up to 32K ctx
1 GPU · 3 Mac classes · 4 device families
RTX 5090~73Simulate output on RTX 5090M5 Max36 GB~20Simulate output on Mac Studio M5 Max (36 GB)M532 GB~7Simulate output on MacBook Air 13" M5 (32 GB)Orin~8Simulate output on NVIDIA Jetson AGX Orin 32GBSnapdragon X Elite (X1E-80-100)~6Simulate output on Snapdragon X Elite Copilot+ PC
By VRAM tier · typical GPUs and Macs at BF16
Similar models
6| Model | Score | VRAM | tok/s | Why it is similar |
|---|---|---|---|---|
| Ling 3.0 TinyInclusion AI | — | 5.5 GB | ~364 | same size |
| BitCPM CANN 8BOpenBMB | — | 5.6 GB | ~127 | same size |
| Gemma 4 E4BGoogle | — | 5.6 GB | ~123 | same size |
| Olmo 3 7B InstructAllen AI | — | 8.4 GB | ~114 | same size |
| Phi Mini MoE InstructMicrosoft | — | 5.4 GB | ~239 | same size |
| Gemma 3n E4B ITGoogle | — | 7.7 GB | ~127 | same size |
Specifications
- Publisher
- Apple
- Parameters
- 7.8B
- Architecture
- LlavaQwen2ForCausalLM
- Context Length
- 32,768 tokens
- Vocabulary Size
- 152,064
- Release Date
- 2025-08-25
- License
- apple-amlr
Frequently Asked Questions
How much VRAM does FastVLM 7B need?
FastVLM 7B requires 15.9 GB of VRAM at BF16. Full 33K context adds up to 1.8 GB (17.7 GB total).
VRAM = Weights + KV Cache + Overhead
Weights = 7.8B × 16 bits ÷ 8 = 15.5 GB
KV Cache + Overhead ≈ 0.4 GB (at 2K context + ~0.3 GB framework)
Fit ratings and hardware model lists check this model with room for a 16K-token context, which needs a little more memory.
KV Cache + Overhead ≈ 2.2 GB (at full 33K context)
VRAM usage by quantization
Can I run FastVLM 7B on a Mac?
Yes — Mac Mini M5 Pro (24 GB) and 106 other Macs can run FastVLM 7B. Apple Silicon uses unified memory, so the model shares RAM with the system. At BF16 you need at least 15.9 GB of usable unified memory (RAM minus macOS overhead).
Can I run FastVLM 7B locally?
Yes — FastVLM 7B can run locally on consumer hardware. Popular tools include Ollama, LM Studio, and llama.cpp.
How fast is FastVLM 7B?
At BF16, FastVLM 7B can reach ~301 tok/s on AMD Instinct MI350X. On NVIDIA GeForce RTX 4090: ~41 tok/s. Speed depends mainly on GPU memory bandwidth. Real-world results typically within ±20%.
tok/s = (bandwidth GB/s ÷ model GB) × efficiency
Example: NVIDIA B200 → 8000 ÷ 15.95 × 0.65 = ~326 tok/s
Estimated speed at BF16 (15.9 GB)
Real-world results typically within ±20%. Speed depends on batch size, quantization kernel, and software stack.
What's the download size of FastVLM 7B?
At BF16, the download is about 15.53 GB.
Which GPUs can run FastVLM 7B?
26 consumer GPUs can run FastVLM 7B at BF16. Top options include AMD Radeon RX 7900 XTX, NVIDIA GeForce RTX 3090, NVIDIA GeForce RTX 3090 Ti, AMD Radeon RX 6800. 7 GPUs have plenty of headroom for comfortable inference.
Which devices can run FastVLM 7B?
122 devices with unified memory can run FastVLM 7B at BF16 (15.9 GB), including AMD Ryzen AI 9 HX 370 (Strix Point) Laptop, ASUS Ascent GX10, Beelink GTR9 Pro (Ryzen AI Max+ 395, 128 GB), Framework Desktop (Ryzen AI Max+ 395, 128 GB). Apple Silicon Macs use unified memory shared between CPU and GPU, making them well-suited for local LLM inference.